stanford_alpaca

stanford_alpaca copied to clipboard

When I prompted Alpaca with ~800 tokens I got this error: Token indices sequence length is longer than the specified maximum sequence length for this model (521 > 512). Running...

teknium1

vampirelzy

whao

train.py doesn't work

1

``` python3 train.py --output_dir ./model Downloading (…)lve/main/config.json: 100%|███████████████████████████████████████████████████████████████████████████████████| 651/651 [00:00

iceja-net

Data License

1

Can we consider reverting the data license to include commercial use? Lots of models are being released using the alpaca dataset (e.g. https://www.databricks.com/blog/2023/03/24/hello-dolly-democratizing-magic-chatgpt-open-models.html).

mjsteele12

ValueError: Your setup doesn't support bf16/gpu. You need torch>=1.10, using Ampere GPU with cuda>=11.0

10

Is Ampere GPU with cuda 11.0 a necessary condition? How to solve this error? Thank you

GUORUIWANG

How to install and run this on Ubuntu server?

11

How to install and run this on Ubuntu server? TIA

rajendrap123

can any one help me with how to use deepspeed in training?

1

kiran1501

Hello, I am following Alpacas one by one. I have followed the current regen.jsonl and output the result as below. ``` [ { "instruction": "Retrieve the biggest peak in the...

daje0601

License question

5

Hello. LLAMA is custom-licensed product of meta, which distributed only for research purposes. Alpaca based on llama. Does it means that using of alpaca in commercial products is illegal?

andrey-pr